© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19938
    Prev
    Next
    INDEX
    Explanations

    ordre du jour

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å«¡
    -0.09
    atrix
    -0.08
    è£ħéħį
    -0.08
    ç¾²
    -0.08
    esp
    -0.08
     кÑĢÑĥ
    -0.08
    å½ķ
    -0.08
    loat
    -0.08
    bsp
    -0.07
    çīĮ
    -0.07
    POSITIVE LOGITS
    marsh
    0.10
    è¿Ļç¯ĩ
    0.10
    åħĪçĶŁ
    0.09
    åĩłå®¶
    0.09
    åĩłå¼ł
    0.09
    ä»ĭ
    0.09
    åĬ³
    0.09
    è¦ģä¸įè¦ģ
    0.08
    .JSONException
    0.08
     Kad
    0.08
    Activations Density 0.081%

    No Known Activations